© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 25846
    Prev
    Next
    INDEX
    Explanations

    phrases that contain repeated conjunctions, particularly "and."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    161
    +0.14
    0.8%
    148
    +0.14
    0.8%
    492
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.14
    0.45
    209
    +0.14
    0.29
    402
    +0.12
    0.26
    Negative Logits
     adoption
    -1.40
     Leah
    -1.39
    ught
    -1.36
     repository
    -1.35
     moduli
    -1.32
     departure
    -1.30
    aset
    -1.28
    duced
    -1.28
     repositories
    -1.28
    ffected
    -1.26
    POSITIVE LOGITS
    ļ
    5.58
    ¯
    5.49
    Ĥ¬
    5.33
    ¾
    5.24
    <|outofrange|>
    5.24
    5.24
    ↵  ↵
    5.24
    ↵↵
    5.24
                  ↵
    5.24
    <|outofrange|>
    5.24
    Activations Density 1.566%

    No Known Activations